© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130653
    Prev
    Next
    INDEX
    Explanations

    Cam Cafe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.07
     eig
    -0.06
     offend
    -0.06
     I
    -0.06
     you
    -0.06
    restrict
    -0.05
    ંબ
    -0.05
     gmail
    -0.05
     presenter
    -0.05
     UDP
    -0.05
    POSITIVE LOGITS
     מה
    0.07
     dazzling
    0.06
     येथ
    0.06
     skillfully
    0.06
    товой
    0.06
     gdzie
    0.06
     כמה
    0.06
     кілька
    0.06
    particularly
    0.06
    corresponding
    0.06
    Activations Density 0.024%

    No Known Activations